[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <9cb78f76-7ab9-4b60-974e-8620bac69424@paulmck-laptop>
Date: Thu, 7 Nov 2024 06:59:02 -0800
From: "Paul E. McKenney" <paulmck@...nel.org>
To: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Cc: Boqun Feng <boqun.feng@...il.com>, Vlastimil Babka <vbabka@...e.cz>,
Marco Elver <elver@...gle.com>, linux-kernel@...r.kernel.org,
kasan-dev@...glegroups.com, linux-mm@...ck.org,
sfr@...b.auug.org.au, longman@...hat.com, cl@...ux.com,
penberg@...nel.org, rientjes@...gle.com, iamjoonsoo.kim@....com,
akpm@...ux-foundation.org, Tomas Gleixner <tglx@...utronix.de>,
Peter Zijlstra <peterz@...radead.org>
Subject: Re: [PATCH 2/2] scftorture: Use a lock-less list to free memory.
On Thu, Nov 07, 2024 at 03:43:00PM +0100, Sebastian Andrzej Siewior wrote:
> On 2024-11-07 06:08:35 [-0800], Paul E. McKenney wrote:
> …
> > This statement in scf_torture_cleanup() is supposed to wait for all
> > outstanding IPIs:
> >
> > smp_call_function(scf_cleanup_handler, NULL, 0);
>
> This should be
> smp_call_function(scf_cleanup_handler, NULL, 1);
>
> so it queues the function call and waits for its completion. Otherwise
> it is queued and might be invoked _later_.
>
> > And the scf_cleanup_handler() function is as follows:
> >
> > static void scf_cleanup_handler(void *unused)
> > {
> > }
> >
> > Does that work, or am I yet again being overly naive?
>
> See above. I can send a patch later on if you have no other complains ;)
You got me on that one! Thank you, and please do feel free to send
a patch.
Interestingly enough, this has never failed. Perhaps because the usual
scftorture run injects enough idle time that all the IPIs have time
to finish. ;-)
Thanx, Paul
Powered by blists - more mailing lists